© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13029
    Prev
    Next
    INDEX
    Explanations

    references to axes and their configurations in mechanical or geometrical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bonner
    -0.45
     Premier
    -0.40
    Premier
    -0.39
    Renato
    -0.39
     Pritchard
    -0.39
    tB
    -0.37
     Premi
    -0.36
    forn
    -0.36
    er
    -0.35
    、“
    -0.35
    POSITIVE LOGITS
    Axis
    1.29
     Axis
    1.28
     axis
    1.25
     AXIS
    1.16
    axis
    1.13
     Axes
    1.09
    AXIS
    1.04
     eixo
    0.99
    軸
    0.97
     axes
    0.96
    Activations Density 0.067%

    No Known Activations